run locally
Browse files
app.py
CHANGED
|
@@ -105,7 +105,7 @@ def main():
|
|
| 105 |
elif provider == 'huggingface':
|
| 106 |
if llm_name is not None and embed_name is not None:
|
| 107 |
os.environ['HFTOKEN'] = str(llm_key)
|
| 108 |
-
Settings.llm = HuggingFaceInferenceAPI
|
| 109 |
model_name=llm_name,
|
| 110 |
token=os.environ.get("HFTOKEN"),
|
| 111 |
temperature=temperature,
|
|
@@ -116,7 +116,7 @@ def main():
|
|
| 116 |
token=os.environ.get("HFTOKEN"),
|
| 117 |
)
|
| 118 |
Settings.num_output = MAX_OUTPUT_TOKENS
|
| 119 |
-
Settings.embed_model = HuggingFaceInferenceAPIEmbedding
|
| 120 |
model_name=embed_name
|
| 121 |
)
|
| 122 |
# Settings.context_window = 4096
|
|
|
|
| 105 |
elif provider == 'huggingface':
|
| 106 |
if llm_name is not None and embed_name is not None:
|
| 107 |
os.environ['HFTOKEN'] = str(llm_key)
|
| 108 |
+
Settings.llm = HuggingFaceLLM( # HuggingFaceInferenceAPI
|
| 109 |
model_name=llm_name,
|
| 110 |
token=os.environ.get("HFTOKEN"),
|
| 111 |
temperature=temperature,
|
|
|
|
| 116 |
token=os.environ.get("HFTOKEN"),
|
| 117 |
)
|
| 118 |
Settings.num_output = MAX_OUTPUT_TOKENS
|
| 119 |
+
Settings.embed_model = HuggingFaceEmbedding( # HuggingFaceInferenceAPIEmbedding
|
| 120 |
model_name=embed_name
|
| 121 |
)
|
| 122 |
# Settings.context_window = 4096
|